Characterizing Speed Performance Of Multi-agent Reinforcement Learning

Abstract

Multi-Agent Reinforcement Learning (MARL) has achieved significant success in large-scale AI systems and big-data applications such as smart grids, surveillance, etc. Existing advancements in MARL algorithms focus on improving the rewards obtained by introducing various mechanisms for inter-agent cooperation. However, these optimizations are usually compute- and memory-intensive, thus leading to suboptimal speed performance in end-to-end training time. In this work, we analyze the speed performance (i.e., latency-bounded throughput) as the key metric in MARL implementations. Specifically, we first introduce a taxonomy of MARL algorithms from an acceleration perspective categorized by (1) training scheme and (2) communication method. Using our taxonomy, we identify three state-of-the-art MARL algorithms - Multi-Agent Deep Deterministic Policy Gradient (MADDPG), Target-oriented Multi-agent Communication and Cooperation (ToM2C), and Networked Multi-Agent RL (NeurComm) - as target benchmar

Stats

• citations3
• S2 citations—
• github stars0
• HF likes0
• heat score4.52
• arxiv keywiggins2023characterizing

Related papers

• Marllib: A Scalable And Efficient Multi-agent Reinforcement Learning Library (2022)0.00
• Benchmarking Multi-agent Deep Reinforcement Learning Algorithms In Cooperative Tasks (2020)0.00
• Towards A Standardised Performance Evaluation Protocol For Cooperative MARL (2022)0.00
• Multi-agent Reinforcement Learning In Stochastic Networked Systems (2020)0.00
• An Initial Introduction To Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Model-based Multi-agent Reinforcement Learning: Recent Progress And Prospects (2022)0.00
• Adaptability In Multi-agent Reinforcement Learning: A Framework And Unified Review (2025)0.00
• A Review Of Cooperative Multi-agent Deep Reinforcement Learning (2019)19.08